{"as_of":"2026-08-16T19:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e551200dc55df4eacbcc92d1e7af40a3d584dbc824936f677efcdca7f775db50","coverage":[{"denominator":23,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":23,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:36:42.055701Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-22T13:22:37.107679Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-22T13:24:53.306749Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"cited_work":{"arxiv_id":"1908.02802","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1908.02802","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Siyan Zhao, Tung Nguyen, and Aditya Grover","venue":null,"work_id":"4ff2a6cd-ba36-48fe-971c-adcdf4e30885","year":1908},"citing_paper":{"arxiv_id":"2510.03271","last_updated":"2026-05-21T09:16:49Z","snapshot_observed_at":"2026-08-15T23:38:04.218346Z","submitted_at":"2025-09-27T07:42:54Z","title":"Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-22T13:22:37.107679Z"},"links":{"cited_paper":"/paper/1908.02802","citing_paper":"/paper/2510.03271"},"observation_digest":"sha256:e88d6f48b7be0db01f56ddb85294da91b192b9269da2a54684e32bc19cac4862","observation_id":"db2f097a-5a13-4fc5-a2cf-95b4cfd2abc2","resolution":{"observed_at":"2026-05-22T13:24:53.309543Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1908.02802/citation-record","integrity":"/paper/1908.02802/integrity","json":"/paper/1908.02802/citation-record.json","paper":"/paper/1908.02802"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.382578Z","title":"Large margin deep networks for classification","venue":null,"work_id":"23f9712d-4dd7-427b-8a80-b073596df95a","year":2018},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:41.960146Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:8009a9881441f4964e1bb18f0539db876f3f0cb30f2c61a5c6a64d2c4444af13","observation_id":"ad783b83-56ab-4484-90a8-b4d96c9bec0f","resolution":{"observed_at":"2026-08-14T14:36:42.386953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.370927Z","title":"The robustness of deep networks: A geometrical perspective","venue":null,"work_id":"f38bb292-fd5a-4af6-81f4-5b4bff9553e3","year":2017},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:41.965323Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:b7fe9bc81e27680e0bfa1b5bc26c118f928c0f89d4c31b8d3f280ba91b979ba1","observation_id":"09073253-9da3-4386-9301-d463bca980d5","resolution":{"observed_at":"2026-08-14T14:36:42.374919Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.357500Z","title":"Empirical study of the topology and geometry of deep networks","venue":null,"work_id":"4692dba5-202a-4a23-ab7b-a8ed738ef559","year":2018},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:41.969483Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:7dd0eedb41ab138ff3538bfda151a08fa6949c591209dfff06c5cc6b7e0e5d58","observation_id":"24d20aff-c015-4694-9193-138af9aca2e6","resolution":{"observed_at":"2026-08-14T14:36:42.362121Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.345240Z","title":"Matrix Computations","venue":null,"work_id":"754d2385-3f06-4f0c-ab54-540575bfeee1","year":2012},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:41.973718Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:3b5d1c8e26681d00f0b2d5e0be8c91a0bd5d96e35f7e262943257ad3e710d69b","observation_id":"a3b27eef-10bd-48e5-b85c-febf5c708f1c","resolution":{"observed_at":"2026-08-14T14:36:42.349249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-12T17:13:46.394331Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-14T14:36:41.978006Z","title":"Explaining and harnessing adversarial examples","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:41.978006Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:cb2e59e857cbb324dde5de6e18a17dddc7d284112a9a23826ef3afcc78d0e223","observation_id":"89e11a19-2fcd-454d-be13-157d01614c89","resolution":{"observed_at":"2026-08-14T14:36:41.978006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.332167Z","title":"Formal guarantees on the robustness of a classifier against adversarial manipulation","venue":null,"work_id":"c6966c56-f94f-4580-ba3f-b99f0840d06f","year":2017},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:41.983684Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:e69344f9fedb7e08bdf9e5f2daeadad9c4c336b9c1dee850a20405946b21c20d","observation_id":"45b52447-6996-4655-b868-4b577c48b984","resolution":{"observed_at":"2026-08-14T14:36:42.336762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.02175","last_updated":"2019-08-12T14:36:10Z","snapshot_observed_at":"2026-08-14T16:36:33.861447Z","submitted_at":"2019-05-06T17:45:05Z","title":"Adversarial Examples Are Not Bugs, They Are Features","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.02175","snapshot_observed_at":"2026-08-14T14:36:41.988210Z","title":"Adversarial examples are not bugs, they are features","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:41.988210Z"},"links":{"cited_paper":"/paper/1905.02175","citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:34c29336f8582bf07ded5761398e53872841d256d67f03dd16d86408462ad5c2","observation_id":"d1a2985f-7c30-4d7e-b21b-ee827653a502","resolution":{"observed_at":"2026-08-14T14:36:41.988210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.319951Z","title":"With friends like these, who needs adversaries? In Advances in Neural Information Processing Systems (NeurIPS 2018), pages 10749--10759, 2018","venue":null,"work_id":"59cd7464-f7db-4bb2-a93a-80f640648634","year":2018},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:41.992657Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:baa1dd69e2e06843a359f1a883a4cc0429bca3a3f78f9d07557de72056c13d48","observation_id":"9aadc593-a1d0-4df7-85cb-a70c4c59b7c0","resolution":{"observed_at":"2026-08-14T14:36:42.324280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.307907Z","title":"Predicting the generalization gap in deep networks with margin distributions","venue":null,"work_id":"4e3583b2-9afb-4172-a604-8c4341c62485","year":2019},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:41.996321Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:d87db3aa9e2ddde27822e288f1aa09d1ccc2a28e4531b38f6f0b8ccff4a0697e","observation_id":"c9d34055-7c65-49e7-83b4-09f70569f126","resolution":{"observed_at":"2026-08-14T14:36:42.312017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.294134Z","title":null,"venue":null,"work_id":"814dbc06-cd1a-4e37-a776-aca2aa5d9302","year":2014},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.000738Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:9dfb7080d917da1dd883cfbdd945a5b01af6ebe7f9074bed4a4f4f998b24f3d6","observation_id":"93716db6-7eb1-4565-8bcf-6caf82f9e445","resolution":{"observed_at":"2026-08-14T14:36:42.299903Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.282273Z","title":"An introduction to computing with neural nets","venue":null,"work_id":"ec731d9d-9c43-4d34-aa21-29a26dd91e3e","year":1987},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.005103Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:dccaf04bd8246040d75682175709cdcd4f31a65ccc15bf18e58879d560023e2d","observation_id":"6206c877-1a6e-49da-9622-351837c5861c","resolution":{"observed_at":"2026-08-14T14:36:42.286498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.269765Z","title":"Margin maximization for robust classification using deep learning","venue":null,"work_id":"e2a37abb-b998-4d50-abf6-f972cc6d3e72","year":2017},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.009085Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:b15b4e6f3da71b29461eb468c339aa741223bc7de43d608d44c7ad729d7ac64d","observation_id":"42605eb8-f0fe-4677-a3ef-62d6eb2a45c0","resolution":{"observed_at":"2026-08-14T14:36:42.273850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.257325Z","title":"Deepfool: a simple and accurate method to fool deep neural networks","venue":null,"work_id":"1ceb6cd9-8ed1-451c-a16d-5c81c40aedb7","year":2016},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.013138Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:55c144c600878747a7da2406c8c7f67ada4947da143e385de4b9285bd5743c67","observation_id":"94ed83fd-32ac-4b4c-b06a-bacd22b26055","resolution":{"observed_at":"2026-08-14T14:36:42.261675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.243974Z","title":"Exploring generalization in deep learning","venue":null,"work_id":"13a5006b-5185-4271-bd24-3e77e71cf34d","year":2017},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.017333Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:6f70a2717158620d5a18f136e8d82bc4deceadf0e067e45cbf88861a483850eb","observation_id":"364cbd2d-e823-4a88-ae14-6e8d6b4d36c8","resolution":{"observed_at":"2026-08-14T14:36:42.248732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.229850Z","title":"Why should I trust you?: Explaining the predictions of any classifier","venue":null,"work_id":"94f10969-52d3-42bd-8efc-036cdabcb91f","year":2016},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.021509Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:19126bcd8e4a7307132ec8b13c3cbe16aca4f766d42387b30a9233a9d2288c93","observation_id":"52706a77-8d32-4085-bc81-904847ad3603","resolution":{"observed_at":"2026-08-14T14:36:42.234691Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.10861","last_updated":"2019-01-30T14:39:32Z","snapshot_observed_at":"2026-08-14T17:23:38.267460Z","submitted_at":"2019-01-30T14:39:32Z","title":"A Simple Explanation for the Existence of Adversarial Examples with Small Hamming Distance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.10861","snapshot_observed_at":"2026-08-14T14:36:42.026061Z","title":"A simple explanation for the existence of adversarial examples with small Hamming distance","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.026061Z"},"links":{"cited_paper":"/paper/1901.10861","citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:41da76d1fb939a36ff28d55ba581c6fc8ff748fa80c01062075566179697e9be","observation_id":"5950ad7d-cd26-4407-a7c3-bf92c248c702","resolution":{"observed_at":"2026-08-14T14:36:42.026061Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.216041Z","title":"Actionable recourse in linear classification","venue":null,"work_id":"ef53f455-1f9b-4c8b-96bd-310fe95ab1cc","year":2018},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.030554Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:03a7d58d743cc562065dfa0eab593ed8e26b3d72ccff2a6f18018b51b97d3a72","observation_id":"d7bec65b-9162-4823-af8b-cc1c4caf69a5","resolution":{"observed_at":"2026-08-14T14:36:42.220466Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.07690","last_updated":"2016-08-27T10:44:54Z","snapshot_observed_at":"2026-08-16T13:09:16.212708Z","submitted_at":"2016-08-27T10:44:54Z","title":"A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.07690","snapshot_observed_at":"2026-08-14T14:36:42.034948Z","title":"A boundary tilting persepective on the phenomenon of adversarial examples","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.034948Z"},"links":{"cited_paper":"/paper/1608.07690","citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:85109621c6c9a0679162e93aa128c0fe476bfe05891fd586491a10db98267479","observation_id":"893143c3-e2b1-43c2-b1ae-1c211c6a3c6d","resolution":{"observed_at":"2026-08-14T14:36:42.034948Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.202814Z","title":"Robustness may be at odds with accuracy","venue":null,"work_id":"c5573f9b-e774-4ca1-8146-997b7ada7e1f","year":2019},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.039411Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:1e042f1899df8819b58f872367544d19473b9f33c380298ce3aff8dc9b29a1fd","observation_id":"379dcdc8-9f68-4824-a68f-633626c99429","resolution":{"observed_at":"2026-08-14T14:36:42.207188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.190091Z","title":"A tutorial on spectral clustering","venue":null,"work_id":"d6cce7a6-b03f-4cbf-99f6-f2c530b60234","year":2007},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.044009Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:286e3c3e0dc232bd013af84eb286cd7971b2e3f8ea5c20a0711c7a3b40cfc544","observation_id":"1a493205-2109-4233-b560-2f102ccbc593","resolution":{"observed_at":"2026-08-14T14:36:42.194524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.175574Z","title":"On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming","venue":null,"work_id":"0a885171-18cd-43b2-b651-acec4834829c","year":2006},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.048074Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:cfd751089d9f35ded7dce42b54d5a3ec2d3cd80145a2ffb81ad2b9146d3558dd","observation_id":"a8ac3c08-addd-4505-93c0-8cfba18df9bd","resolution":{"observed_at":"2026-08-14T14:36:42.180298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:42.161865Z","title":"Counterfactual explanations without opening the black box: Automated decisions and the GDPR","venue":null,"work_id":"8749ca1c-6ed0-4768-ac75-4ee71e53585a","year":2018},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.051939Z"},"links":{"citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:e1384b93fb6a892fca6d6e81c72edd967e2ac59c9e9bccf5d7665aecae04f76b","observation_id":"008bfb9d-0daf-4ebe-9ae7-88a6d686fe07","resolution":{"observed_at":"2026-08-14T14:36:42.166492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.08789","last_updated":"2019-03-21T01:03:42Z","snapshot_observed_at":"2026-08-14T16:59:06.322512Z","submitted_at":"2019-03-21T01:03:42Z","title":"Interpreting Neural Networks Using Flip Points","version":1},"cited_work":{"arxiv_id":"1903.08789","doi":null,"metadata_source":"pith","pith_arxiv_id":"1903.08789","snapshot_observed_at":"2026-08-14T14:36:42.091215Z","title":"Interpreting Neural Networks Using Flip Points","venue":"cs.LG","work_id":"b0a7c925-9b42-48d7-b9d8-0637098a79ac","year":2019},"citing_paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-14T14:36:42.055701Z"},"links":{"cited_paper":"/paper/1903.08789","citing_paper":"/paper/1908.02802"},"observation_digest":"sha256:53405deb4c7c17ca1c01ad1f425e810bcb1f9baeb2851ff6edf85d86f94bd848","observation_id":"34f0fc81-376c-4705-ac5b-4d3a393c4ea4","resolution":{"observed_at":"2026-08-14T14:36:42.098785Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.02802","last_updated":"2019-08-07T19:09:22Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T22:41:10.733962Z","submitted_at":"2019-08-07T19:09:22Z","title":"Investigating Decision Boundaries of Trained Neural Networks"},"reference_resolution":{"displayed":23,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":1,"verified_fuzzy":17},"total_outbound_references":23},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 1 inbound Pith citation observation for arXiv:1908.02802."}